GitLab

* cache non lora pipeline outputs.

* up

* up

* up

* up

* Revert "up"

This reverts commit 772c32e43397f25919c29bbbe8ef9dc7d581cfb8.

* up

* Revert "up"

This reverts commit cca03df7fce55550ed28b59cadec12d1db188283.

* up

* up

* add .

* up

* up

* up

* up

* up

* up

* change syntax

* make style

* init

* feedback

* feedback

* feedback

* feedback

* feedback

* feedback

* Allow prerelease when installing transformers from main

* maybe better

* maybe better

* and now?

* just bored

* should be better

* works now

fix xpu ut failures w/ latest pytorch
Signed-off-by: Yao, Matrix <matrix.yao@intel.com>

* update

* update

* update

* update

* update

* fix

* add mellon node registry

* style

* update docstring to include more info!

* support custom node mellon

* HTTPErrpr -> HfHubHTTPErrpr

* up

* Update src/diffusers/modular_pipelines/qwenimage/node_utils.py

* init

* config

* lora metadata

* feedback

* fix

* cache allocator warmup for from_single_file

* feedback

* feedback

* init

* feedback

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* feat: support aobaseconfig classes.

* [docs] AOBaseConfig (#12302)

init
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* up

* replace with is_torchao_version

* up

* up

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* fix: preserve boolean dtype for attention masks in ChromaPipeline

- Convert attention masks to bool and prevent dtype corruption
- Fix both positive and negative mask handling in _get_t5_prompt_embeds
- Remove float conversion in _prepare_attention_mask method

Fixes #12116

* test: add ChromaPipeline attention mask dtype tests

* test: add slow ChromaPipeline attention mask tests

* chore: removed comments

* refactor: removing redundant type conversion

* Remove dedicated dtype tests as per  feedback

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

u[

* start unbloating docstrings (save_lora_weights).

* load_lora_weights()

* lora_state_dict

* fuse_lora

* unfuse_lora

* load_lora_into_transformer

* slight edits to the attention backends docs.

* Update docs/source/en/optimization/attention_backends.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* disable installing transformers from main in ci for now.

* up

* u[p

* Support huggingface_hub 0.x and 1.x

* httpx

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* misc: update examples link

* misc: update examples link

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* docs: introduce cache-dit to diffusers

* Refine documentation for CacheDiT features

Updated the wording for clarity and consistency in the documentation. Adjusted sections on cache acceleration, automatic block adapter, patch functor, and hybrid cache configuration.

* update

* update

* add coauthor
Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>

* improve test

* handle ip adapter params correctly

* fix chroma qkv fusion test

* fix fastercache implementation

* fix more tests

* fight more tests

* add back set_attention_backend

* update

* update

* make style

* make fix-copies

* make ip adapter processor compatible with attention dispatcher

* refactor chroma as well

* remove rmsnorm assert

* minify and deprecate npu/xla processors

* update

* refactor

* refactor; support flash attention 2 with cp

* fix

* support sage attention with cp

* make torch compile compatible

* update

* refactor

* update

* refactor

* refactor

* add ulysses backward

* try to make dreambooth script work; accelerator backward not playing well

* Revert "try to make dreambooth script work; accelerator backward not playing well"

This reverts commit 768d0ea6fa6a305d12df1feda2afae3ec80aa449.

* workaround compilation problems with triton when doing all-to-all

* support wan

* handle backward correctly

* support qwen

* support ltx

* make fix-copies

* Update src/diffusers/models/modeling_utils.py
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* apply review suggestions

* update docs

* add explanation

* make fix-copies

* add docstrings

* support passing parallel_config to from_pretrained

* apply review suggestions

* make style

* update

* Update docs/source/en/api/parallel.md
Co-authored-by: Aryan <aryan@huggingface.co>

* up

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>

Fixed WanVACEPipeline to allow prompt to be None and skip encoding step

Signed-off-by: Yao, Matrix <matrix.yao@intel.com>

Signed-off-by: Yao, Matrix <matrix.yao@intel.com>

disable xformer tests for pipelines it isn't popular.

* update

* update

* update

* single scheduler please.

* up

* up

* up

* init

* feedback

* update

* feedback

* fixes

* update

* update

* init

* toctree

* scheduler suggestions

* toctree

* Fixes chroma docs

* fix docs

fixed docs are now consistent

* up

* xfail some tests

* up

* up

* factor out the overlaps in save_lora_weights().

* remove comment.

* remove comment.

* up

* fix-copies

* FIxes enable_xformers_memory_efficient_attention()

* Update attention.py

xfail some kandinsky tests.

* Upgrade huggingface-hub to version 0.35.0

Updated huggingface-hub version from 0.26.1 to 0.35.0.

* Add uvicorn and accelerate to requirements

* Fix install instructions for server

* feat: add support of qwenimageeditplus

* add copies statement

* fix copies statement

* remove vl_processor reference

update

* Convert alphas for embedders for sd-scripts to ai toolkit conversion

* Add kohya embedders conversion test

* Apply style fixes

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

Add RequestScopedPipeline for safe concurrent inference, tokenizer lock and non-mutating retrieve_timesteps (#12328)

* Basic implementation of request scheduling

* Basic editing in SD and Flux Pipelines

* Small Fix

* Fix

* Update for more pipelines

* Add examples/server-async

* Add examples/server-async

* Updated RequestScopedPipeline to handle a single tokenizer lock to avoid race conditions

* Fix

* Fix _TokenizerLockWrapper

* Fix _TokenizerLockWrapper

* Delete _TokenizerLockWrapper

* Fix tokenizer

* Update examples/server-async

* Fix server-async

* Optimizations in examples/server-async

* We keep the implementation simple in examples/server-async

* Update examples/server-async/README.md

* Update examples/server-async/README.md for changes to tokenizer locks and backward-compatible retrieve_timesteps

* The changes to the diffusers core have been undone and all logic is being moved to exmaples/server-async

* Update examples/server-async/utils/*

* Fix BaseAsyncScheduler

* Rollback in the core of the diffusers

* Update examples/server-async/README.md

* Complete rollback of diffusers core files

* Simple implementation of an asynchronous server compatible with SD3-3.5 and Flux Pipelines

* Update examples/server-async/README.md

* Fixed import errors in 'examples/server-async/serverasync.py'

* Flux Pipeline Discard

* Update examples/server-async/README.md

* Apply style fixes

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* fix hidream type hint

* fix hunyuan-video type hint

* fix many type hint

* fix many type hint errors

* fix many type hint errors

* fix many type hint errors

* make stype & make quality

* Update autoencoder_kl_wan.py

When using the Wan2.2 VAE, the spatial compression ratio calculated here is incorrect. It should be 16 instead of 8. Pass it in directly via the config to ensure it’s correct here.

* Update autoencoder_kl_wan.py